> ## Documentation Index
> Fetch the complete documentation index at: https://docs.pipecat.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Pipecat Clients

> Client SDKs for building real-time voice and multimodal AI applications with Pipecat.

Pipecat's client SDKs connect your users to Pipecat agents running on the server. They handle the real-time media layer — microphone and camera access, audio playback, transport connections, and the event stream from your bot — so you can focus on building your application.

<Card title="Quickstart" icon="rocket" href="/client/get-started/quickstart">
  Build and run your first Pipecat voice application
</Card>

## Available SDKs

<CardGroup cols={3}>
  <Card title="JavaScript" icon="js" color="#f7e014" href="/api-reference/client/js/overview">
    Core SDK for web applications
  </Card>

  <Card title="React" icon="react" color="#56c4db" href="/api-reference/client/react/overview">
    Hooks and components for React apps
  </Card>

  <Card title="React Native" icon="react" color="#56c4db" href="/api-reference/client/react-native/overview">
    iOS and Android via React Native
  </Card>

  <Card title="iOS" icon="swift" color="#F05138" href="/api-reference/client/ios/overview">
    Native Swift SDK for iOS
  </Card>

  <Card title="Android" icon="android" color="#78C257" href="/api-reference/client/android/overview">
    Native Kotlin SDK for Android
  </Card>

  <Card title="C++" icon="c" color="#679cd3" href="/api-reference/client/cpp/overview">
    Native SDK for desktop and embedded
  </Card>
</CardGroup>

## How It Fits Together

Pipecat's architecture is split between server and client. The server runs your AI pipeline — speech recognition, LLM, text-to-speech — and the client connects your user to it over a real-time transport.

<Frame>
  <img src="https://mintcdn.com/daily/v9a5HDZcmVbZAs6t/images/client-server-architecture.png?fit=max&auto=format&n=v9a5HDZcmVbZAs6t&q=85&s=c185f004136179447acc598ddf6c0091" width="2606" height="454" data-path="images/client-server-architecture.png" />
</Frame>

The client SDKs implement the [RTVI standard](/client/rtvi-standard) — an open protocol for real-time AI inference — which means they work with any RTVI-compatible server, not just Pipecat.

## What the SDKs Handle

* **Transport management** — establishing, maintaining, and tearing down connections
* **Media capture** — microphone and camera device access and streaming
* **Audio playback** — rendering bot audio output
* **Session state** — tracking connection state and bot readiness
* **Event stream** — callbacks and events for transcriptions, bot speaking, errors, and more
* **Messaging** — sending custom messages to your bot and handling responses

## Ready to Build?

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/client/get-started/quickstart">
    Get a voice conversation running in minutes
  </Card>

  <Card title="Core Concepts" icon="book-open" href="/client/rtvi-standard">
    Understand transports, sessions, events, and media
  </Card>

  <Card title="API Reference" icon="code" href="/api-reference/client/js/overview">
    Full reference for all SDK methods, hooks, and callbacks
  </Card>

  <Card title="Examples" icon="github" href="https://github.com/pipecat-ai/pipecat-examples">
    Complete example applications across all platforms
  </Card>
</CardGroup>